@pi5549

'3/4/5-levels' looks like a very powerful way of explaining concepts. I'd like to see the higher levels be longer, and really drill down into the heart of the matter. So that the  final level is communicating at an expert level. +1 / subbed.

@paramino

This is very good intro for quick understanding of the concept 👍

@synthoelectro

now that's some quantum technology, man... Being one of the beta testers of Stable Diffusion helps me understand this even more.

@GouravKhanduri

Learnt a lot about diffusion models, thanks for the video

@CharlieYou823

you're so beautiful and explain the Diffusion model in the most simple way. as the chinese saying: 人狠话不多！:rocket-red-countdown-liftoff:

@jenzi8944

Very clear intro, thanks!

@user-wr4yl7tx3w

This was so helpful. Love this format of starting easier and add layers of explanations.

@mr.osophy

Such a great video to dive in! I'm live streaming learning about Diffusion, right now!

@Simplegrandeur1162

Great video for beginners! Really helpful, Thank you!

@sinsernadeesoyo

This video was awesome! Well done :) and thank you

@MrMc2BOB

Your explanation helped me a lot to better understand this interesting process. The only technical term I had to look up was: neural convolutional network.
This technical term refers to a digital brain that is specially trained to recognize visual patterns. It is characterized by its ability to identify local features in images and process this information hierarchically.
All in all, thank You for your explanation

@Kaleubs

Thanks for this video, this was very insightfull. Still have a lot to learn about this topic that will revolutionize our world so much

@JanMatusiewicz

Thanks for clear explanations and link to the blog!

@yousufmamsa

Great explanation of diffusion models. Thank you.

@hamidzemirline7318

thanks for this great presentation

@OpuYT

Thank you for your explanation!

@AbuzarbhuttaG

❤🎉 amazing lecture

@uquantum

Thanks so much for a useful presentation…what a good idea to present in several levels!

@cosmingurau

Sorry, but I don't understand something very important. WHY would you add the noise and then substract the noise? Correct me if I'm wrong, but the rightmost noise image in this example is basically an encoded image of the original dog image, that can be decoded deterministically with the neural network, in multiple steps. That's nice and dandy. And I do understand that the noise image is not like a RAR archive, which, were it to be slightly modified, would just yield corruption errors, and instead the modified noise image would still generate... an image. NOW. 

1. How do you get from the user text prompt to the noise image of what the user WANTED, that will THEN be denoised (decoded)?
2. How is it so that not every OTHER noise result from the text prompt (except previously deterministically encoded images like this dog image for example) will output just a bunch of garbled mess? And yes, I know that is sometimes the case, I used Stable Diffusion daily.

@shashankshekharsingh2912

Now, that's a great explanation for Diffusion Models.